Category

API

App

SophNet
Date
Price

sophnet/DeepSeek-V3.2-Fast

The high-TPS, ultra-fast version of DeepSeek V3.2, reaching up to 100 t/s.
Model
LLM
Model capability: thinkingModel capability: function_call
Input:
$1.143/1M tokensstarting from
Output:
$3.429/1M tokensstarting from

sophnet/DeepSeek-V3.2

The open-source large model with a multi-expert mixture-of-experts (MoE) architecture launched by DeepSeek.
Model
LLM
Model capability: thinkingModel capability: function_call
Input:
$0.286/1M tokens
Output:
$0.429/1M tokens

sophnet/LongCat-Flash-Thinking

The enhanced "Deep Thinking" version of LongCat-Flash-Chat, specifically designed for handling complex logic, mathematical, and programming tasks.
Model
LLM
Model capability: function_call
Input:
$0.143/1M tokens
Output:
$1.429/1M tokens

sophnet/Kimi-K2-0905

Enhanced Encoding and MultiModal Machine Learning Compatible Large Model
Model
LLM
Model capability: function_call
Input:
$0.572/1M tokens
Output:
$2.286/1M tokens

sophnet/LongCat-Flash-Chat

The efficient Mixture-of-Experts (MoE) language model released and open-sourced by Meituan's technical team.
Model
LLM
Input:
$0.143/1M tokens
Output:
$0.714/1M tokens

sophnet/DeepSeek-V3.1-Fast

The high-performance, ultra-fast version of DeepSeek V3.1 Terminus, featuring a significantly improved response speed, is ideal for application scenarios that require rapid interaction.
Model
LLM
Model capability: function_call
Input:
$1.143/1M tokens
Output:
$3.4286/1M tokens

sophnet/GLM-4.5V

Multimodal Visual Reasoning Model Based on the MOE Architecture
Model
LLM
Model capability: image
Input:
$0.286/1M tokens
Output:
$0.8572/1M tokens